{"total":117,"rows":[{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410,"area":null},{"id":"2110.04994","title":"Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans","created":"2021-10-11","cited_by_count":336,"area":null},{"id":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327,"area":null},{"id":"2109.06780","title":"Benchmarking the Spectrum of Agent Capabilities","created":"2021-09-14","cited_by_count":200,"area":null},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166,"area":null},{"id":"2207.13751","title":"GAUDI: A Neural Architect for Immersive 3D Scene Generation","created":"2022-07-27","cited_by_count":136,"area":null},{"id":"2104.00670","title":"Unconstrained Scene Generation with Locally Conditioned Radiance Fields","created":"2021-04-01","cited_by_count":130,"area":null},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97,"area":null},{"id":"2109.00157","title":"A Survey of Exploration Methods in Reinforcement Learning","created":"2021-09-01","cited_by_count":73,"area":null},{"id":"2206.10558","title":"EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine","created":"2022-06-21","cited_by_count":62,"area":null},{"id":"2303.01859","title":"POPGym: Benchmarking Partially Observable Reinforcement Learning","created":"2023-03-03","cited_by_count":62,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2210.05805","title":"Exploration via Elliptical Episodic Bonuses","created":"2022-10-11","cited_by_count":51,"area":null},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47,"area":null},{"id":"2210.02019","title":"Atari-5: Distilling the Arcade Learning Environment down to Five Games","created":"2022-10-05","cited_by_count":44,"area":null},{"id":"2110.10067","title":"CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents","created":"2021-10-19","cited_by_count":38,"area":null},{"id":"2206.01078","title":"Deep Transformer Q-Networks for Partially Observable Reinforcement Learning","created":"2022-06-02","cited_by_count":36,"area":null},{"id":"2108.11544","title":"Vision-Language Navigation: A Survey and Taxonomy","created":"2021-08-26","cited_by_count":34,"area":null},{"id":"2103.03216","title":"Continuous Coordination As a Realistic Scenario for Lifelong Learning","created":"2021-03-04","cited_by_count":32,"area":null},{"id":"2110.05721","title":"Action-Sufficient State Representation Learning for Control with Structural Constraints","created":"2021-10-12","cited_by_count":31,"area":null},{"id":"2106.13948","title":"Core Challenges in Embodied Vision-Language Planning","created":"2021-06-26","cited_by_count":30,"area":null},{"id":"2301.11181","title":"Deep Laplacian-based Options for Temporally-Extended Exploration","created":"2023-01-26","cited_by_count":29,"area":null},{"id":"2106.00596","title":"Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks","created":"2021-06-01","cited_by_count":26,"area":null},{"id":"2412.00887","title":"Playable Game Generation","created":"2024-12-01","cited_by_count":26,"area":null},{"id":"2106.15877","title":"Experience-Driven PCG via Reinforcement Learning: A Super Mario Bros Study","created":"2021-06-30","cited_by_count":25,"area":null},{"id":"2212.11110","title":"Lifelong Reinforcement Learning with Modulating Masks","created":"2022-12-21","cited_by_count":22,"area":null},{"id":"2107.08170","title":"Megaverse: Simulating Embodied Agents at One Million Experiences per Second","created":"2021-07-17","cited_by_count":20,"area":null},{"id":"2302.07515","title":"TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play","created":"2023-02-15","cited_by_count":20,"area":null},{"id":"2103.07013","title":"Large Batch Simulation for Deep Reinforcement Learning","created":"2021-03-12","cited_by_count":19,"area":null},{"id":"2110.05769","title":"Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents","created":"2021-10-12","cited_by_count":19,"area":null},{"id":"2406.19236","title":"Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions","created":"2024-06-27","cited_by_count":19,"area":null},{"id":"2208.14226","title":"Unsupervised Representation Learning in Deep Reinforcement Learning: A Review","created":"2022-08-27","cited_by_count":18,"area":null},{"id":"2107.06011","title":"Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation","created":"2021-07-13","cited_by_count":17,"area":null},{"id":"2103.12300","title":"Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration","created":"2021-03-23","cited_by_count":15,"area":null},{"id":"2508.08601","title":"Yan: Foundational Interactive Video Generation","created":"2025-08-12","cited_by_count":15,"area":null},{"id":"2304.13269","title":"Games for Artificial Intelligence Research: A Review and Perspectives","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2107.08241","title":"High-Accuracy Model-Based Reinforcement Learning, a Survey","created":"2021-07-17","cited_by_count":13,"area":null},{"id":"2208.03374","title":"Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter","created":"2022-08-05","cited_by_count":13,"area":null},{"id":"2103.11374","title":"MaAST: Map Attention with Semantic Transformersfor Efficient Visual Navigation","created":"2021-03-21","cited_by_count":11,"area":null},{"id":"2104.06411","title":"Subgoal-based Reward Shaping to Improve Efficiency in Reinforcement Learning","created":"2021-04-13","cited_by_count":11,"area":null},{"id":"2106.10060","title":"Contrastive Learning of Generalized Game Representations","created":"2021-06-18","cited_by_count":11,"area":null},{"id":"2112.03899","title":"Information is Power: Intrinsic Control via Information Capture","created":"2021-12-07","cited_by_count":11,"area":null},{"id":"2207.13649","title":"Explain My Surprise: Learning Efficient Long-Term Memory by Predicting Uncertain Outcomes","created":"2022-07-27","cited_by_count":11,"area":null},{"id":"2506.14990","title":"MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning","created":"2025-06-17","cited_by_count":11,"area":null},{"id":"2207.12051","title":"Flowsheet synthesis through hierarchical reinforcement learning and graph neural networks","created":"2022-07-25","cited_by_count":10,"area":null},{"id":"2212.06988","title":"Efficient Exploration in Resource-Restricted Reinforcement Learning","created":"2022-12-14","cited_by_count":10,"area":null},{"id":"2308.07822","title":"Deep reinforcement learning for process design: Review and perspective","created":"2023-08-15","cited_by_count":10,"area":null},{"id":"2210.06702","title":"A Mixture of Surprises for Unsupervised Reinforcement Learning","created":"2022-10-13","cited_by_count":9,"area":null},{"id":"2509.03682","title":"A Comprehensive Review of Multi-Agent Reinforcement Learning in Video Games","created":"2025-09-03","cited_by_count":9,"area":null},{"id":"2306.07124","title":"Diverse Projection Ensembles for Distributional Reinforcement Learning","created":"2023-06-12","cited_by_count":8,"area":null},{"id":"2108.02846","title":"Communicative Learning with Natural Gestures for Embodied Navigation Agents with Human-in-the-Scene","created":"2021-08-05","cited_by_count":7,"area":null},{"id":"2110.12985","title":"Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning","created":"2021-10-25","cited_by_count":7,"area":null},{"id":"2202.10881","title":"Coordinate-Aligned Multi-Camera Collaboration for Active Multi-Object Tracking","created":"2022-02-22","cited_by_count":7,"area":null},{"id":"2205.07060","title":"GAN-Aimbots: Using Machine Learning for Cheating in First Person Shooters","created":"2022-05-14","cited_by_count":7,"area":null},{"id":"2207.11584","title":"Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning","created":"2022-07-23","cited_by_count":7,"area":null},{"id":"2304.12164","title":"USA-Net: Unified Semantic and Affordance Representations for Robot Memory","created":"2023-04-24","cited_by_count":7,"area":null},{"id":"2307.01676","title":"RaidEnv: Exploring New Challenges in Automated Content Balancing for Boss Raid Games","created":"2023-07-04","cited_by_count":7,"area":null},{"id":"2503.02505","title":"ROCKET-2: Steering Visuomotor Policy via Cross-View Goal Alignment","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2503.14229","title":"HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactions","created":"2025-03-18","cited_by_count":7,"area":null},{"id":"2105.04488","title":"A Deep Reinforcement Learning Approach to Audio-Based Navigation in a Multi-Speaker Environment","created":"2021-05-10","cited_by_count":6,"area":null},{"id":"2107.07394","title":"Explore and Control with Adversarial Surprise","created":"2021-07-12","cited_by_count":6,"area":null},{"id":"2202.10057","title":"CCPT: Automatic Gameplay Testing and Validation with Curiosity-Conditioned Proximal Trajectories","created":"2022-02-21","cited_by_count":6,"area":null},{"id":"2203.07454","title":"L2Explorer: A Lifelong Reinforcement Learning Assessment Environment","created":"2022-03-14","cited_by_count":6,"area":null},{"id":"2206.06490","title":"Learning Task-Independent Game State Representations from Unlabeled Images","created":"2022-06-13","cited_by_count":6,"area":null},{"id":"2102.12103","title":"FIXAR: A Fixed-Point Deep Reinforcement Learning Platform with Quantization-Aware Training and Adaptive Parallelism","created":"2021-02-24","cited_by_count":5,"area":null},{"id":"2203.16777","title":"Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks","created":"2022-03-31","cited_by_count":5,"area":null},{"id":"2212.04581","title":"PALMER: Perception-Action Loop with Memory for Long-Horizon Planning","created":"2022-12-08","cited_by_count":5,"area":null},{"id":"2306.07552","title":"Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second","created":"2023-06-13","cited_by_count":5,"area":null},{"id":"2107.02195","title":"Agents that Listen: High-Throughput Reinforcement Learning with Multiple Sensory Systems","created":"2021-07-05","cited_by_count":4,"area":null},{"id":"2205.07444","title":"A Deep Reinforcement Learning Blind AI in DareFightingICE","created":"2022-05-16","cited_by_count":4,"area":null},{"id":"2210.10595","title":"DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation","created":"2022-10-19","cited_by_count":4,"area":null},{"id":"2607.06701","title":"SPEAR: A Simulator for Photorealistic Embodied AI Research","created":"2026-07-07","cited_by_count":4,"area":null},{"id":"2107.00703","title":"Distilling Reinforcement Learning Tricks for Video Games","created":"2021-07-01","cited_by_count":3,"area":null},{"id":"2306.01066","title":"Investigating Navigation Strategies in the Morris Water Maze through Deep Reinforcement Learning","created":"2023-06-01","cited_by_count":3,"area":null},{"id":"2307.11141","title":"Towards General Game Representations: Decomposing Games Pixels into Content and Style","created":"2023-07-20","cited_by_count":3,"area":null},{"id":"2606.24893","title":"AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2106.10112","title":"Deep Reinforcement Learning Models Predict Visual Responses in the Brain: A Preliminary Result","created":"2021-06-18","cited_by_count":2,"area":null},{"id":"2107.11965","title":"Playtesting: What is Beyond Personas","created":"2021-07-26","cited_by_count":2,"area":null},{"id":"2108.04097","title":"Deep Learning for Embodied Vision Navigation: A Survey","created":"2021-07-07","cited_by_count":2,"area":null},{"id":"2305.13741","title":"L-SA: Learning Under-Explored Targets in Multi-Target Reinforcement Learning","created":"2023-05-23","cited_by_count":2,"area":null},{"id":"2306.17766","title":"Comparing Reinforcement Learning and Human Learning using the Game of Hidden Rules","created":"2023-06-30","cited_by_count":2,"area":null},{"id":"2410.11330","title":"Evolutionary Retrofitting","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2105.00762","title":"VECA : A Toolkit for Building Virtual Environments to Train and Test Human-like Agents","created":"2021-05-03","cited_by_count":1,"area":null},{"id":"2105.13806","title":"DRL: Deep Reinforcement Learning for Intelligent Robot Control -- Concept, Literature, and Future","created":"2021-04-20","cited_by_count":1,"area":null},{"id":"2107.06149","title":"MINERVAS: Massive INterior EnviRonments VirtuAl Synthesis","created":"2021-07-13","cited_by_count":1,"area":null},{"id":"2110.12778","title":"A Deep Reinforcement Learning Approach for Audio-based Navigation and Audio Source Localization in Multi-speaker Environments","created":"2021-10-25","cited_by_count":1,"area":null},{"id":"2111.08096","title":"VisualEnv: visual Gym environments with Blender","created":"2021-11-15","cited_by_count":1,"area":null},{"id":"2205.03555","title":"Multi-Target Active Object Tracking with Monte Carlo Tree Search and Target Motion Modeling","created":"2022-05-07","cited_by_count":1,"area":null},{"id":"2205.09448","title":"Image Augmentation Based Momentum Memory Intrinsic Reward for Sparse Reward Visual Scenes","created":"2022-05-19","cited_by_count":1,"area":null},{"id":"2208.04832","title":"On the Importance of Critical Period in Multi-stage Reinforcement Learning","created":"2022-08-09","cited_by_count":1,"area":null},{"id":"2210.09026","title":"WILD-SCAV: Benchmarking FPS Gaming AI on Unity3D-based Environments","created":"2022-10-14","cited_by_count":1,"area":null},{"id":"2301.11891","title":"Polycraft World AI Lab (PAL): An Extensible Platform for Evaluating Artificial Intelligence Agents","created":"2023-01-27","cited_by_count":1,"area":null},{"id":"2303.01013","title":"Domain Adaptation of Reinforcement Learning Agents based on Network Service Proximity","created":"2023-03-02","cited_by_count":1,"area":null},{"id":"2311.15960","title":"Program Machine Policy: Addressing Long-Horizon Tasks by Integrating Program Synthesis and State Machines","created":"2023-11-27","cited_by_count":1,"area":null},{"id":"2411.13072","title":"AMaze: An intuitive benchmark generator for fast prototyping of generalizable agents","created":"2024-11-20","cited_by_count":1,"area":null},{"id":"2504.06468","title":"Agent-Arena: A General Framework for Evaluating Control Algorithms","created":"2025-04-08","cited_by_count":1,"area":null},{"id":"2604.08340","title":"Mastering PokeGym: Graph-Guided Multimodal Evolution at Test Time","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2106.01607","title":"Grounding Complex Navigational Instructions Using Scene Graphs","created":"2021-06-03","cited_by_count":0,"area":null},{"id":"2112.00583","title":"Meta Arcade: A Configurable Environment Suite for Meta-Learning","created":"2021-12-01","cited_by_count":0,"area":null}],"next_cursor":"100"}